Merge pull request #5974 from y-p/PR_info_max_info_rows

ENH: revamp null count supression for large frames in df.info()

Author: y-p

doc/source/release.rst

@@ -72,6 +72,7 @@ Improvements to existing features
   - perf improvements in Series datetime/timedelta binary operations (:issue:`5801`)
   - `option_context` context manager now available as top-level API (:issue:`5752`)
   - df.info() view now display dtype info per column (:issue: `5682`)
+  - df.info() now honors option max_info_rows, disable null counts for large frames (:issue: `5974`)
   - perf improvements in DataFrame ``count/dropna`` for ``axis=1``
   - Series.str.contains now has a `regex=False` keyword which can be faster for plain (non-regex) string patterns. (:issue: `5879`)
   - support ``dtypes`` on ``Panel``

pandas/core/config_init.py

@@ -166,11 +166,9 @@
 
 pc_max_info_rows_doc = """
 : int or None
-    Deprecated.
-"""
-
-pc_max_info_rows_deprecation_warning = """\
-max_info_rows has been deprecated, as reprs no longer use the info view.
+    df.info() will usually show null-counts for each column.
+    For large frames this can be quite slow. max_info_rows and max_info_cols
+    limit this null check only to frames with smaller dimensions then specified.
 """
 
 pc_large_repr_doc = """
@@ -266,9 +264,6 @@ def mpl_style_cb(key):
                     msg=pc_height_deprecation_warning,
                     rkey='display.max_rows')
 
-cf.deprecate_option('display.max_info_rows',
-                    msg=pc_max_info_rows_deprecation_warning)
-
 tc_sim_interactive_doc = """
 : boolean
     Whether to simulate interactive mode for purposes of testing

pandas/core/frame.py

@@ -1419,20 +1419,35 @@ def info(self, verbose=True, buf=None, max_cols=None):
             max_cols = get_option(
                 'display.max_info_columns', len(self.columns) + 1)
 
-        if verbose and len(self.columns) <= max_cols:
+        max_rows = get_option('display.max_info_rows', len(self) + 1)
+
+        show_counts = ((len(self.columns) <= max_cols) and
+                         (len(self) < max_rows))
+        if verbose:
             lines.append('Data columns (total %d columns):' %
                          len(self.columns))
             space = max([len(com.pprint_thing(k)) for k in self.columns]) + 4
-            counts = self.count()
-            if len(cols) != len(counts):  # pragma: no cover
-                raise AssertionError('Columns must equal counts (%d != %d)' %
-                                     (len(cols), len(counts)))
+            counts = None
+
+            tmpl = "%s%s"
+            if show_counts:
+                counts = self.count()
+                if len(cols) != len(counts):  # pragma: no cover
+                    raise AssertionError('Columns must equal counts (%d != %d)' %
+                                         (len(cols), len(counts)))
+                tmpl =  "%s non-null %s"
+
             dtypes = self.dtypes
-            for col, count in compat.iteritems(counts):
+            for i, col in enumerate(self.columns):
                 dtype = dtypes[col]
                 col = com.pprint_thing(col)
+
+                count= ""
+                if show_counts:
+                    count = counts[i]
+
                 lines.append(_put_str(col, space) +
-                             '%d non-null %s' % (count, dtype))
+                             tmpl % (count, dtype))
         else:
             lines.append(self.columns.summary(name='Columns'))